Triple
T12187977
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Elephant Man |
E290384
|
entity |
| Predicate | leadPerformanceReception |
P103655
|
FINISHED |
| Object | John Hurt performance widely praised |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: John Hurt performance widely praised | Statement: [The Elephant Man, leadPerformanceReception, John Hurt performance widely praised]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leadPerformanceReception Context triple: [The Elephant Man, leadPerformanceReception, John Hurt performance widely praised]
-
A.
leadSingle
Indicates that an entity serves as the primary or featured performer, contributor, or focus in a single work or instance.
-
B.
leadNation
Indicates that one entity holds the primary leadership role or governing authority over a nation.
-
C.
leadHijacker
Indicates that one entity is the primary organizer or chief perpetrator among a group of hijackers involved in a hijacking event.
-
D.
leadsInto
Indicates that one entity serves as an entry or transition point that directly connects or opens into another entity.
-
E.
leadCallAndResponsePartner
Indicates a relationship where one entity initiates a call-and-response interaction and the other serves as its primary responding partner.
- F. None of above. chosen
Provenance (4 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d6ab64de5881908d56eb7a75c6cc69 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d91a83012c81908d04bbab5fdcd8c2 |
completed | April 10, 2026, 3:42 p.m. |
| PD | Predicate disambiguation | batch_69d91510a258819090ef8fbdc2d8707b |
completed | April 10, 2026, 3:19 p.m. |
| PDg | Predicate description generation | batch_69d91a7e0fc081909ec9769231e728a4 |
completed | April 10, 2026, 3:42 p.m. |
Created at: April 8, 2026, 9:50 p.m.